- Notifications
You must be signed in to change notification settings - Fork65
Official implementation of Score-CAM in PyTorch
License
haofanwang/Score-CAM
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
We develop a novel post-hoc visual explanation method called Score-CAM, which is the first gradient-free CAM-based visualization method that achieves better visual performance (state-of-the-art).
Paper:Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks, appeared at IEEECVPR 2020 Workshop on Fair, Data Efficient and Trusted Computer Vision. Our paper has been cited by400!
Demo: You can run an example viaColab
2021.12.16: A great MATLAB implementation fromKenta Itakura.
2021.4.03: A Pytorch implementationjacobgil/pytorch-grad-cam (3.8K Stars).
2020.8.18: A PaddlePaddle implementation fromPaddlePaddle/InterpretDL.
2020.7.11: A Tensorflow implementation fromkeisen/tf-keras-vis.
2020.5.11: A Pytorch implementation fromutkuozbulak/pytorch-cnn-visualizations (6.2K Stars).
2020.3.24: Merged intofrgfm/torch-cam, a wonderful library that supports multiple CAM-based methods.
If you find this work is helpful in your research, please cite our work:
@inproceedings{wang2020score, title={Score-CAM: Score-weighted visual explanations for convolutional neural networks}, author={Wang, Haofan and Wang, Zifan and Du, Mengnan and Yang, Fan and Zhang, Zijian and Ding, Sirui and Mardziel, Piotr and Hu, Xia}, booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops}, pages={24--25}, year={2020}}Utils are built onflashtorch, thanks for releasing this great work!
If you have any questions, feel free to open an issue or directly contact me via:haofanwang.ai@gmail.com.